Abstract
Basically, Deep learning has become more popular in present day generation. This is very cheaper and easier to use. In this paper the design of DBN (Dynamic Bayesian Network) deep learning architecture is implemented for edge cloud computing analytics by using markov decision process. The main intent of edge and cloud computing is to overcome the problem of over traffic that is occurred while data is transmitting. The data analytics while analyze the complexity occurred in the system. Here data reduction block is introduced on the edge with ML on the cloud. Hence this paper will investigate the edge cloud computing for data analytics and introduces an deep learning approach for reducing data on the ML on edge cloud computing from the simulation results, it can observe that comparison of normal and DBN server communication power efficiency. Similarly, the speed of server communication also shown.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call